{"id":"https://openalex.org/W4408345832","doi":"https://doi.org/10.1109/icassp49660.2025.10888703","title":"ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement","display_name":"ZipEnhancer: Dual-Path Down-Up Sampling-based Zipformer for Monaural Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345832","doi":"https://doi.org/10.1109/icassp49660.2025.10888703"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016797242","display_name":"Haoxu Wang","orcid":"https://orcid.org/0000-0002-5430-0899"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069657933","display_name":"Biao Tian","orcid":"https://orcid.org/0000-0001-7259-3739"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Tian","raw_affiliation_strings":["Alibaba Group,Speech Lab,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016797242"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":4.9574,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94128169,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9503999948501587,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9395999908447266,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.746666431427002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820463538169861},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5670002698898315},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5509013533592224},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5369635820388794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5362623929977417},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5023360252380371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20768070220947266},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19419926404953003},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1301860213279724},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1143692135810852}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.746666431427002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820463538169861},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5670002698898315},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5509013533592224},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5369635820388794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5362623929977417},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5023360252380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20768070220947266},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19419926404953003},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1301860213279724},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1143692135810852},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2094721231","https://openalex.org/W2476548250","https://openalex.org/W2603567530","https://openalex.org/W2801554275","https://openalex.org/W2892009249","https://openalex.org/W2935934262","https://openalex.org/W2937484199","https://openalex.org/W2940417587","https://openalex.org/W2962843322","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3015485199","https://openalex.org/W3015974384","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3158779859","https://openalex.org/W3163652268","https://openalex.org/W3197729725","https://openalex.org/W3197813307","https://openalex.org/W3206809722","https://openalex.org/W4221143458","https://openalex.org/W4221162870","https://openalex.org/W4224917453","https://openalex.org/W4232282348","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W4385807442","https://openalex.org/W4385822313","https://openalex.org/W4385823093","https://openalex.org/W4391021752","https://openalex.org/W4392902507","https://openalex.org/W4392902873","https://openalex.org/W4392903232","https://openalex.org/W4392904015","https://openalex.org/W4392904222","https://openalex.org/W4395447416","https://openalex.org/W4402111568","https://openalex.org/W4402112151","https://openalex.org/W4403126475","https://openalex.org/W4406461266","https://openalex.org/W4410314146","https://openalex.org/W6838276489","https://openalex.org/W6857062747"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2944394647","https://openalex.org/W2072124114","https://openalex.org/W2538939196"],"abstract_inverted_index":{"In":[0],"contrast":[1],"to":[2,32,60,98],"other":[3,136],"sequence":[4],"tasks":[5],"modeling":[6],"hidden":[7,34],"layer":[8,35],"features":[9,36],"with":[10,37,117,138],"three":[11],"axes,":[12],"Dual-Path":[13,45,78],"time":[14,54],"and":[15,23,55,72,84,93,114,127,132],"time-frequency":[16],"domain":[17,57],"speech":[18,122],"enhancement":[19],"models":[20],"are":[21,28],"effective":[22],"have":[24],"low":[25],"parameters":[26,131],"but":[27],"computationally":[29],"demanding":[30],"due":[31],"their":[33],"four":[38],"axes.":[39],"We":[40,64],"propose":[41,73],"ZipEnhancer,":[42],"which":[43],"is":[44],"Down-Up":[46,58],"Sampling-based":[47],"Zipformer":[48],"for":[49],"Monaural":[50],"Speech":[51],"Enhancement,":[52],"incorporating":[53],"frequency":[56],"sampling":[59],"reduce":[61],"computational":[62],"costs.":[63],"introduce":[65,89],"the":[66,69,74,77,90,100,110],"ZipformerBlock":[67],"as":[68],"core":[70],"block":[71],"design":[75],"of":[76,121,125],"DownSampleStacks":[79],"that":[80],"symmetrically":[81],"scale":[82,85],"down":[83],"up.":[86],"Also,":[87],"we":[88],"ScaleAdam":[91],"optimizer":[92],"Eden":[94],"learning":[95],"rate":[96],"scheduler":[97],"improve":[99],"performance":[101],"further.":[102],"Our":[103],"model":[104],"achieves":[105],"new":[106],"state-of-the-art":[107],"results":[108],"on":[109],"DNS":[111],"2020":[112],"Challenge":[113],"Voicebank+DEMAND":[115],"datasets,":[116],"a":[118],"perceptual":[119],"evaluation":[120],"quality":[123],"(PESQ)":[124],"3.69":[126],"3.63,":[128],"using":[129],"2.04M":[130],"62.41G":[133],"FLOPS,":[134],"outperforming":[135],"methods":[137],"similar":[139],"complexity":[140],"levels.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}